Model type
Biomolecular diffusion structure predictor with protein language-model features
ESMFold2 predicts biomolecular structures from protein, DNA, RNA and ligand inputs, optionally using protein alignments.
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Biomolecular diffusion structure predictor with protein language-model features
Protein, DNA/RNA, modified-residue and small-molecule specifications; optional protein MSAs for the full variant.
All-atom complex coordinates with confidence estimates and optional distogram predictions.
Official project documentation and implementation: https://github.com/evolutionaryscale/esm
limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
1 evaluation · 1 metric rows. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: ESMFold2 (MSA, 10 loops) | Protocol: ESMFold2 Runs N’ Poses reported comparison msa: Runs N’ Poses ligand pass rate (MSA) Dataset subset: Runs N’ Poses complete-case intersection: 2,573 scored ligands (ESMFold2 Runs N’ Poses reported comparison split) | 67% ligand_pass_rate percent · higher Uncertainty: Not reported Coverage: unit: ligands; scored: 2573; eligible: unreported; note: Complete-case intersection; source 2600 systems is not a ligand denominator. | Author-reported evaluation · source checkedMethods, coverage and sourceRuns N’ Poses receptor–ligand co-folding; source benchmark 2,600 systems. Figure 2C reports n=2,573 scored ligands on the intersection where all models produced valid predictions, after excluding undefined SuCOS scores. Multiple ligands in one system are scored independently. Five seeds × five diffusion samples per target; select top candidate by ipTM. Success requires lDDT-PLI >0.8 and BiSyRMSD <2 angstrom. Baselines use 10 recycles and 200 diffusion steps; ESMFold2 uses 10 or 20 loops as labelled and truncated 68-step diffusion. Single-sequence and MSA conditions remain separate. Aggregation: Not reported ESMFold2 primary paper v1, Figure 2C Runs N’ Poses · PDF page 5, Figure 2C, Runs N’ Poses subpanel (right), msa block, bar 10 from left (ESMFold2 (MSA, 10 loops)), exact printed bar label |
Source checking is not independent reproduction. Release 2026-09-23-2b89723c6dd9.
Related profile: ESMFold2. This page retains the exact record and its evaluation context.
Author-evaluated folding configuration with conditioning and loop count retained from Figure 2C.
ESMFold2 predicts biomolecular structures from protein, DNA, RNA and ligand inputs, optionally using protein alignments. ESM C 6B embeddings coupled to a diffusion-based structure prediction architecture. The documented inputs are protein, DNA/RNA, modified-residue and small-molecule specifications; optional protein MSAs for the full variant. The output consists of all-atom complex coordinates with confidence estimates and optional distogram predictions.
ESMFold2 supports optional MSA conditioning; ESMFold2-Fast is a distinct single-sequence inference variant. The applicable input limits require configuration-specific checking.
Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.
Stable record: discovery-model-esmfold2Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Biomolecular diffusion structure predictor with protein language-model featuresSources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Architecture | ESM C 6B embeddings coupled to a diffusion-based structure prediction architecture.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Inputs | Protein, DNA/RNA, modified-residue and small-molecule specifications; optional protein MSAs for the full variant.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Outputs | All-atom complex coordinates with confidence estimates and optional distogram predictions.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Parameters | The official card identifies a 6B ESM C backbone. It does not state a total including the complete molecular structure and confidence modules. · Not reported in inspected sourcesSources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Known versions | ESMFold2 supports optional MSA conditioning; ESMFold2-Fast is a distinct single-sequence inference variant.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Training data | The checked model card identifies PDB structures and AlphaFoldDB-derived training data.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Training cutoff | September 2021 is the model-card data cutoff for both ESMFold2 and ESMFold2-Fast; the separate ESMC backbone corpus has its own provenance.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Context limits | The inspected card describes Full and Fast variants without giving a single maximum token/atom budget that applies to every supported molecular composition. · Not reported in inspected sourcesSources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Weights licence | MIT declared in the official ESMFold2 card, with linked third-party dependency notices.Sources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Access | Official project documentation and implementation: https://github.com/evolutionaryscale/esmSources (5)evolutionaryscale/esm: README.md; evolutionaryscale/esm: _assets/ESM3_README.md; evolutionaryscale/esm: THIRD_PARTY_NOTICE.md; biohub/ESMFold2: README.md; biohub/ESMFold2: config.json · Official biohub/ESMFold2 card: Model Details, Model Variants, Training Data and Biases and Limitations; official source README and THIRD_PARTY_NOTICE.md |
| Code licence | MITSourcesevolutionaryscale/esm: LICENSE.md · LICENSE.md: licence text |
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: family discovery-model-esmfold2 Individual claims | ESMFold2 primary paper v1, Figure 2C Runs N’ Poses Figure 2C Runs N’ Poses, bar label ESMFold2 (MSA, 10 loops); Appendix A.2.10 Version: 10.64898/2026.06.03.729735v1; posted 2026-06-04 | source checked automated source review · 2026-09-23 Audit detailsSource-backed evaluated identity only; no independent reproduction. Field: Claim: esmfold2-2026-runs-n-poses-method-esmfold2-msa-10-loops-discovery-model-esmfold2-identity-claim Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
View linked audit checks and correction history
Release 2026-09-23-2b89723c6dd9 · Record review: source checked
Stable ID: esmfold2-2026-runs-n-poses-method-esmfold2-msa-10-loops